EDPNet (高效DB和PARSeq网络):在具有挑战性的场景下,为在线数字计量器检测和识别提供强大的框架
Songwen Guan1, Zhitian Niu1, Ming Kong1
1College of Metrology Measurement and Instrument, China Jiliang University, Hangzhou 310048, China.
Sensors (Basel, Switzerland)
|April 26, 2025
概括
这项研究介绍了EDPNet,这是自动计量器读数的高效框架. 它通过整合边界检测和文本识别,在具有挑战性的条件下提高了准确性和稳定性,优于现有的方法.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 人工智能的人工智能
背景情况:
- 自动计数器读数面临着诸如视角扭曲,不规则区域和复杂背景等挑战.
- 当前的方法通常使用对象检测而不进行文本特定优化,并且强度改进侧重于数据而不是架构.
研究的目的:
- 提出一个新的端到端框架,EDPNet (高效DB和PARSeq网络),用于准确和高效的自动计量器读数.
- 通过集成高效的边界检测和文本识别来解决当前系统的局限性.
主要方法:
- EDPNet集成了EDNet用于检测和EPNet用于识别.
- 对于扭曲和背景挑战,EDNet使用EfficientNetV2-s与多尺度KeyDrop注意力 (MSKA) 和高效多尺度注意力 (EMA).
- EPNet将一个DropKey Attention模块集成到PARSeq编码器中,用于不规则的读数识别和过拟减轻.
主要成果:
- 在EDNet的F1得分为0.997988,超过DBNet++的0.61%.
- 在具有挑战性的场景中,EDPNet的性能比最先进的方法优于0.7-1.9%,参数减少了20.03%.
- EPNet的识别准确率达到了90.0%,超过目前最佳性能0.2%.
结论:
- 拟议的EDPNet框架为复杂环境中的自动计量器读取提供了卓越的准确性和稳定性.
- EDPNet是一个轻量级和高效的解决方案,在检测和识别任务中表现优于现有方法.
相关概念视频
Difference from Background: Limit of Detection
4.6K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
4.6K
Electronic Distance Measuring Instruments
16
Electronic Distance Measuring Instruments (EDMs) are essential tools in modern surveying, offering precise distance measurements by emitting electromagnetic signals and calculating the time required for these signals to travel to a target and return. Two primary types of signals are used in EDMs — light waves and microwaves — each suited to specific environmental and distance requirements. Light-wave-based EDMs utilize either infrared or laser light, providing high accuracy over short...
16


